dragon-ml-toolbox 10.7.0__py3-none-any.whl → 10.9.0__py3-none-any.whl

{dragon_ml_toolbox-10.7.0.dist-info → dragon_ml_toolbox-10.9.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dragon-ml-toolbox
-Version: 10.7.0
+Version: 10.9.0
 Summary: A collection of tools for data science and machine learning projects.
 Author-email: Karl Loza <luigiloza@gmail.com>
 License-Expression: MIT

{dragon_ml_toolbox-10.7.0.dist-info → dragon_ml_toolbox-10.9.0.dist-info}/RECORD

@@ -1,36 +1,36 @@
-dragon_ml_toolbox-10.7.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
-dragon_ml_toolbox-10.7.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
+dragon_ml_toolbox-10.9.0.dist-info/licenses/LICENSE,sha256=2uUFNy7D0TLgHim1K5s3DIJ4q_KvxEXVilnU20cWliY,1066
+dragon_ml_toolbox-10.9.0.dist-info/licenses/LICENSE-THIRD-PARTY.md,sha256=lY4_rJPnLnMu7YBQaY-_iz1JRDcLdQzNCyeLAF1glJY,1837
 ml_tools/ETL_cleaning.py,sha256=lSP5q6-ukGhJBPV8dlsqJvPXAzj4du_0J-SbtEd0Pjg,19292
 ml_tools/ETL_engineering.py,sha256=a6KCWH6kRatZtjaFEF_o917ApPMK5_vRD-BjfCDAl-E,49400
 ml_tools/GUI_tools.py,sha256=kEQWg-bog3pB5tI22gMGKWaCGHnz9TB2Lvvfhf5F2CI,45412
 ml_tools/MICE_imputation.py,sha256=kVSythWfxJFR4-2mtcYCWQaQ1Oz5yyx_SJu5gjnS7H8,11670
 ml_tools/ML_callbacks.py,sha256=JPvEw_cW5tYNJ2rMSgnNrKLuni_UrmuhDFaOw-u2SvA,13926
-ml_tools/ML_datasetmaster.py,sha256=uenjHP-Mh4tn20rWSEGN_JsCPvuPNDGW-PElBhb2a4I,30346
-ml_tools/ML_evaluation.py,sha256=28JJ2M71p4pxniwav2Hv3b1a5dsvaoIYNLm-UJQuXvY,16002
+ml_tools/ML_datasetmaster.py,sha256=BMmdCVAZ-HSnnSPLzKla2TdZKvHkHj4t9A0V1Ba3i-I,30821
+ml_tools/ML_evaluation.py,sha256=q4_RsBjmidc_yDX-DQvpJW8RCHrOCJbgXKBORQdt-TM,16111
 ml_tools/ML_evaluation_multi.py,sha256=2jTSNFCu8cz5C05EusnrDyffs59M2Fq3UXSHxo2TR1A,12515
 ml_tools/ML_inference.py,sha256=SGDPiPxs_OYDKKRZziFMyaWcC8A37c70W9t-dMP5niI,23066
-ml_tools/ML_models.py,sha256=A_yeULMxT3IAuJuwIF5nXdAQwQDGsxHlbDSxtlzVG44,27699
+ml_tools/ML_models.py,sha256=FliuqGhxP7AWHCweTLlfssXFOjwvFhIYJsgj_w_-EI4,27901
 ml_tools/ML_optimization.py,sha256=a2Uxe1g-y4I-gFa8ENIM8QDS-Pz3hoPRRaVXAWMbyQA,13491
-ml_tools/ML_scaler.py,sha256=yKVrXW6dWV6UoC9ViLMzORfXQXvGTJvzkNbSrB0F5t0,7447
+ml_tools/ML_scaler.py,sha256=IrZsAr1xjvuLi8s5IKR-qbk2mS_awl3mn_xoXg5TJyA,7535
 ml_tools/ML_trainer.py,sha256=xw1zMgYpdqwsTt604xe3GTQNvpg6z6Ze-avmitGBFeU,23539
 ml_tools/PSO_optimization.py,sha256=q0VYpssQGbPum7xdnkDXlJQKhZMYZo8acHpKhajPK3c,22954
 ml_tools/RNN_forecast.py,sha256=8rNZr-eWOBXMiDQV22e_tQTPM5LM2IFggEAa1FaoXaI,1965
-ml_tools/SQL.py,sha256=WDgdZUYuLBUpv-4Am9XjVY_Aq_jxBWdLrbcgAIEwefI,10704
+ml_tools/SQL.py,sha256=givoz6CGWRUdqnBem3VGZxzGdo3ZbX00kyHNjzI8kWE,10803
 ml_tools/VIF_factor.py,sha256=MkMh_RIdsN2XUPzKNGRiEcmB17R_MmvGV4ezpL5zD2E,10403
 ml_tools/__init__.py,sha256=q0y9faQ6e17XCQ7eUiCZ1FJ4Bg5EQqLjZ9f_l5REUUY,41
 ml_tools/_logger.py,sha256=wcImAiXEZKPNcwM30qBh3t7HvoPURonJY0nrgMGF0sM,4719
 ml_tools/_script_info.py,sha256=21r83LV3RubsNZ_RTEUON6RbDf7Mh4_udweNcvdF_Fk,212
 ml_tools/custom_logger.py,sha256=ry43hk54K6xKo8jRAgq1sFxUpOA9T0LIJ7sw0so2BW0,5880
 ml_tools/data_exploration.py,sha256=4McT2BR9muK4JVVTKUfvRyThe0m_o2vpy9RJ1f_1FeY,28692
-ml_tools/ensemble_evaluation.py,sha256=xMEMfXJ5MjTkTfr1LkFOeD7iUtnVDCW3S9lm3zT-6tY,24778
+ml_tools/ensemble_evaluation.py,sha256=FGHSe8LBI8_w8LjNeJWOcYQ1UK_mc6fVah8gmSvNVGg,26853
 ml_tools/ensemble_inference.py,sha256=EFHnbjbu31fcVp88NBx8lWAVdu2Gpg9MY9huVZJHFfM,9350
 ml_tools/ensemble_learning.py,sha256=3s0kH4i_naj0IVl_T4knst-Hwg4TScWjEdsXX5KAi7I,21929
 ml_tools/handle_excel.py,sha256=He4UT15sCGhaG-JKfs7uYVAubxWjrqgJ6U7OhMR2fuE,14005
-ml_tools/keys.py,sha256=ThuyNnSV4iK712WRaGXEm9uGW8Dg3djKa7HFRmPCRr4,1228
+ml_tools/keys.py,sha256=FDpbS3Jb0pjrVvvp2_8nZi919mbob_-xwuy5OOtKM_A,1848
 ml_tools/optimization_tools.py,sha256=P3I6lIpvZ8Xf2kX5FvvBKBmrK2pB6idBpkTzfUJxTeE,5073
-ml_tools/path_manager.py,sha256=7sRvAoNrboRY6ef9gH3_qdzoZ66iLs7Aii4P39K0kEk,13819
-ml_tools/utilities.py,sha256=SVMaSDigh6SUoAeig2_sXLLIj5w5mUs5KuVWpHvFDec,19816
-dragon_ml_toolbox-10.7.0.dist-info/METADATA,sha256=3yKY50Qa3kt1lvDo_ELk3dUczIunDGuf6bB3UaiBl9g,6968
-dragon_ml_toolbox-10.7.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-dragon_ml_toolbox-10.7.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
-dragon_ml_toolbox-10.7.0.dist-info/RECORD,,
+ml_tools/path_manager.py,sha256=wLJlz3Y9_1-LB9em4B2VYDCVuTOX2eOc7D6hbbebjgM,14990
+ml_tools/utilities.py,sha256=30z0x1aDLyBGzF98_tgSaxwFafYwQS-GTFzXHopBSGc,29105
+dragon_ml_toolbox-10.9.0.dist-info/METADATA,sha256=NK8z4StYOVR0ByF_l-vNjyrFgbb2qddBa6lOzlQsZrg,6968
+dragon_ml_toolbox-10.9.0.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+dragon_ml_toolbox-10.9.0.dist-info/top_level.txt,sha256=wm-oxax3ciyez6VoO4zsFd-gSok2VipYXnbg3TH9PtU,9
+dragon_ml_toolbox-10.9.0.dist-info/RECORD,,

ml_tools/ML_datasetmaster.py

@@ -15,6 +15,8 @@ from ._logger import _LOGGER
 from ._script_info import _script_info
 from .custom_logger import save_list_strings
 from .ML_scaler import PytorchScaler
+from .keys import DatasetKeys
+
 
 __all__ = [
     "DatasetMaker",
@@ -91,6 +93,7 @@ class _BaseDatasetMaker(ABC):
         self.scaler: Optional[PytorchScaler] = None
         self._id: Optional[str] = None
         self._feature_names: List[str] = []
+        self._target_names: List[str] = []
         self._X_train_shape = (0,0)
         self._X_test_shape = (0,0)
         self._y_train_shape = (0,)
@@ -142,6 +145,10 @@ class _BaseDatasetMaker(ABC):
     @property
     def feature_names(self) -> list[str]:
         return self._feature_names
+    
+    @property
+    def target_names(self) -> list[str]:
+        return self._target_names
 
     @property
     def id(self) -> Optional[str]:
@@ -162,10 +169,17 @@ class _BaseDatasetMaker(ABC):
         """Saves a list of feature names as a text file"""
         save_list_strings(list_strings=self._feature_names,
                           directory=directory,
-                          filename="feature_names",
-                          verbose=verbose)    
+                          filename=DatasetKeys.FEATURE_NAMES,
+                          verbose=verbose)
+        
+    def save_target_names(self, directory: Union[str, Path], verbose: bool=True) -> None:
+        """Saves a list of target names as a text file"""
+        save_list_strings(list_strings=self._target_names,
+                          directory=directory,
+                          filename=DatasetKeys.TARGET_NAMES,
+                          verbose=verbose)
 
-    def save_scaler(self, save_dir: Union[str, Path]):
+    def save_scaler(self, save_dir: Union[str, Path], verbose: bool=True) -> None:
         """
         Saves the fitted PytorchScaler's state to a .pth file.
 
@@ -178,14 +192,15 @@ class _BaseDatasetMaker(ABC):
             _LOGGER.error("No scaler was fitted or provided.")
             raise RuntimeError()
         if not self.id: 
-            _LOGGER.error("Must set the `id` before saving scaler.")
+            _LOGGER.error("Must set the dataset `id` before saving scaler.")
             raise ValueError()
         save_path = make_fullpath(save_dir, make=True, enforce="directory")
         sanitized_id = sanitize_filename(self.id)
-        filename = f"scaler_{sanitized_id}.pth"
+        filename = f"{DatasetKeys.SCALER_PREFIX}{sanitized_id}.pth"
         filepath = save_path / filename
-        self.scaler.save(filepath)
-        _LOGGER.info(f"Scaler for dataset '{self.id}' saved to '{filepath.name}'.")
+        self.scaler.save(filepath, verbose=False)
+        if verbose:
+            _LOGGER.info(f"Scaler for dataset '{self.id}' saved to '{filepath.name}'.")
 
 
 # Single target dataset
@@ -203,7 +218,7 @@ class DatasetMaker(_BaseDatasetMaker):
         `train_dataset` -> PyTorch Dataset
         `test_dataset`  -> PyTorch Dataset
         `feature_names` -> list[str]
-        `target_name`   -> str
+        `target_names`  -> list[str]
         `id` -> str
         
     The ID can be manually set to any string if needed, it is the target name by default.
@@ -231,8 +246,8 @@ class DatasetMaker(_BaseDatasetMaker):
         features = pandas_df.iloc[:, :-1]
         target = pandas_df.iloc[:, -1]
         self._feature_names = features.columns.tolist()
-        self._target_name = str(target.name)
-        self._id = self._target_name
+        self._target_names = [str(target.name)]
+        self._id = self._target_names[0]
 
         # --- 2. Split ---
         X_train, X_test, y_train, y_test = train_test_split(
@@ -249,12 +264,8 @@ class DatasetMaker(_BaseDatasetMaker):
         )
         
         # --- 4. Create Datasets ---
-        self._train_ds = _PytorchDataset(X_train_final, y_train.values, labels_dtype=label_dtype, feature_names=self._feature_names, target_names=[self._target_name])
-        self._test_ds = _PytorchDataset(X_test_final, y_test.values, labels_dtype=label_dtype, feature_names=self._feature_names, target_names=[self._target_name])
-
-    @property
-    def target_name(self) -> str:
-        return self._target_name
+        self._train_ds = _PytorchDataset(X_train_final, y_train.values, labels_dtype=label_dtype, feature_names=self._feature_names, target_names=self._target_names)
+        self._test_ds = _PytorchDataset(X_test_final, y_test.values, labels_dtype=label_dtype, feature_names=self._feature_names, target_names=self._target_names)
 
 
 # --- New Multi-Target Class ---
@@ -303,10 +314,6 @@ class DatasetMakerMulti(_BaseDatasetMaker):
         self._train_ds = _PytorchDataset(X_train_final, y_train, labels_dtype=label_dtype, feature_names=self._feature_names, target_names=self._target_names)
         self._test_ds = _PytorchDataset(X_test_final, y_test, labels_dtype=label_dtype, feature_names=self._feature_names, target_names=self._target_names)
 
-    @property
-    def target_names(self) -> list[str]:
-        return self._target_names
-
 
 # --- Private Base Class ---
 class _BaseMaker(ABC):

ml_tools/ML_evaluation.py

@@ -22,6 +22,7 @@ from .path_manager import make_fullpath
 from ._logger import _LOGGER
 from typing import Union, Optional, List
 from ._script_info import _script_info
+from .keys import SHAPKeys
 
 
 __all__ = [
@@ -333,7 +334,8 @@ def shap_summary_plot(model,
     plt.close()
 
     # Save Summary Data to CSV
-    summary_path = save_dir_path / "shap_summary.csv"
+    shap_summary_filename = SHAPKeys.SAVENAME + ".csv"
+    summary_path = save_dir_path / shap_summary_filename
     # Ensure the array is 1D before creating the DataFrame
     mean_abs_shap = np.abs(shap_values).mean(axis=0).flatten()
     
@@ -341,9 +343,9 @@ def shap_summary_plot(model,
         feature_names = [f'feature_{i}' for i in range(len(mean_abs_shap))]
         
     summary_df = pd.DataFrame({
-        'feature': feature_names,
-        'mean_abs_shap_value': mean_abs_shap
-    }).sort_values('mean_abs_shap_value', ascending=False)
+        SHAPKeys.FEATURE_COLUMN: feature_names,
+        SHAPKeys.SHAP_VALUE_COLUMN: mean_abs_shap
+    }).sort_values(SHAPKeys.SHAP_VALUE_COLUMN, ascending=False)
     
     summary_df.to_csv(summary_path, index=False)
     

ml_tools/ML_models.py

@@ -6,7 +6,7 @@ import json
 from ._logger import _LOGGER
 from .path_manager import make_fullpath
 from ._script_info import _script_info
-from .keys import PytorchModelKeys
+from .keys import PytorchModelArchitectureKeys
 
 
 __all__ = [
@@ -29,11 +29,14 @@ class _ArchitectureHandlerMixin:
             raise AttributeError()
 
         path_dir = make_fullpath(directory, make=True, enforce="directory")
-        full_path = path_dir / PytorchModelKeys.SAVENAME
+        
+        json_filename = PytorchModelArchitectureKeys.SAVENAME + ".json"
+        
+        full_path = path_dir / json_filename
 
         config = {
-            PytorchModelKeys.MODEL: self.__class__.__name__,
-            PytorchModelKeys.CONFIG: self.get_architecture_config() # type: ignore
+            PytorchModelArchitectureKeys.MODEL: self.__class__.__name__,
+            PytorchModelArchitectureKeys.CONFIG: self.get_architecture_config() # type: ignore
         }
 
         with open(full_path, 'w') as f:
@@ -48,7 +51,8 @@ class _ArchitectureHandlerMixin:
         user_path = make_fullpath(file_or_dir)
         
         if user_path.is_dir():
-            target_path = make_fullpath(user_path / PytorchModelKeys.SAVENAME, enforce="file")
+            json_filename = PytorchModelArchitectureKeys.SAVENAME + ".json"
+            target_path = make_fullpath(user_path / json_filename, enforce="file")
         elif user_path.is_file():
             target_path = user_path
         else:
@@ -58,8 +62,8 @@ class _ArchitectureHandlerMixin:
         with open(target_path, 'r') as f:
             saved_data = json.load(f)
 
-        saved_class_name = saved_data[PytorchModelKeys.MODEL]
-        config = saved_data[PytorchModelKeys.CONFIG]
+        saved_class_name = saved_data[PytorchModelArchitectureKeys.MODEL]
+        config = saved_data[PytorchModelArchitectureKeys.CONFIG]
 
         if saved_class_name != cls.__name__:
             _LOGGER.error(f"Model class mismatch. File specifies '{saved_class_name}', but '{cls.__name__}' was expected.")

ml_tools/ML_scaler.py

@@ -149,7 +149,7 @@ class PytorchScaler:
         
         return data_clone
 
-    def save(self, filepath: Union[str, Path]):
+    def save(self, filepath: Union[str, Path], verbose: bool=True):
         """
         Saves the scaler's state (mean, std, indices) to a .pth file.
 
@@ -163,10 +163,11 @@ class PytorchScaler:
             'continuous_feature_indices': self.continuous_feature_indices
         }
         torch.save(state, path_obj)
-        _LOGGER.info(f"PytorchScaler state saved to '{path_obj.name}'.")
+        if verbose:
+            _LOGGER.info(f"PytorchScaler state saved to '{path_obj.name}'.")
 
     @staticmethod
-    def load(filepath: Union[str, Path]) -> 'PytorchScaler':
+    def load(filepath: Union[str, Path], verbose: bool=True) -> 'PytorchScaler':
         """
         Loads a scaler's state from a .pth file.
 
@@ -178,7 +179,8 @@ class PytorchScaler:
         """
         path_obj = make_fullpath(filepath, enforce="file")
         state = torch.load(path_obj)
-        _LOGGER.info(f"PytorchScaler state loaded from '{path_obj.name}'.")
+        if verbose:
+            _LOGGER.info(f"PytorchScaler state loaded from '{path_obj.name}'.")
         return PytorchScaler(
             mean=state['mean'],
             std=state['std'],

ml_tools/SQL.py

@@ -4,7 +4,7 @@ from pathlib import Path
 from typing import Union, Dict, Any, Optional, List, Literal
 from ._logger import _LOGGER
 from ._script_info import _script_info
-from .path_manager import make_fullpath
+from .path_manager import make_fullpath, sanitize_filename
 
 
 __all__ = [
@@ -94,11 +94,13 @@ class DatabaseManager:
         if not self.cursor:
             _LOGGER.error("Database connection is not open.")
             raise sqlite3.Error()
+        
+        sanitized_table_name = sanitize_filename(table_name)
 
         columns_def = ", ".join([f'"{col_name}" {col_type}' for col_name, col_type in schema.items()])
         exists_clause = "IF NOT EXISTS" if if_not_exists else ""
         
-        query = f"CREATE TABLE {exists_clause} {table_name} ({columns_def})"
+        query = f"CREATE TABLE {exists_clause} {sanitized_table_name} ({columns_def})"
         
         _LOGGER.info(f"➡️ Executing: {query}")
         self.cursor.execute(query)

ml_tools/ensemble_evaluation.py

@@ -25,6 +25,7 @@ from typing import Union, Optional, Literal
 from .path_manager import sanitize_filename, make_fullpath
 from ._script_info import _script_info
 from ._logger import _LOGGER
+from .keys import SHAPKeys
 
 
 __all__ = [
@@ -472,7 +473,7 @@ def get_shap_values(
         save_dir: Directory to save visualizations.
     """
     sanitized_target_name = sanitize_filename(target_name)
-    global_save_path = make_fullpath(save_dir, make=True)
+    global_save_path = make_fullpath(save_dir, make=True, enforce="directory")
     
     def _apply_plot_style():
         styles = ['seaborn', 'seaborn-v0_8-darkgrid', 'seaborn-v0_8', 'default']
@@ -539,6 +540,15 @@ def get_shap_values(
                         plot_type=plot_type,
                         title=f"{model_name} - {target_name} (Class {class_name})"
                     )
+                    
+                # Save the summary data for the current class
+                summary_save_path = global_save_path / f"SHAP_{sanitized_target_name}_{class_name}.csv"
+                _save_summary_csv(
+                    shap_values_for_summary=class_shap,
+                    feature_names=feature_names,
+                    save_path=summary_save_path
+                )
+                    
         else:
             values = shap_values[1] if isinstance(shap_values, list) else shap_values
             for plot_type in ["bar", "dot"]:
@@ -549,6 +559,15 @@ def get_shap_values(
                     plot_type=plot_type,
                     title=f"{model_name} - {target_name}"
                 )
+                
+            # Save the summary data for the positive class
+            shap_summary_filename = SHAPKeys.SAVENAME + ".csv"
+            summary_save_path = global_save_path / shap_summary_filename
+            _save_summary_csv(
+                shap_values_for_summary=values,
+                feature_names=feature_names,
+                save_path=summary_save_path
+            )
 
     def _plot_for_regression(shap_values):
         for plot_type in ["bar", "dot"]:
@@ -559,6 +578,34 @@ def get_shap_values(
                 plot_type=plot_type,
                 title=f"{model_name} - {target_name}"
             )
+        
+        # Save the summary data to a CSV file
+        shap_summary_filename = SHAPKeys.SAVENAME + ".csv"
+        summary_save_path = global_save_path / shap_summary_filename
+        _save_summary_csv(
+            shap_values_for_summary=shap_values,
+            feature_names=feature_names,
+            save_path=summary_save_path
+        )
+        
+    def _save_summary_csv(shap_values_for_summary: np.ndarray, feature_names: list[str], save_path: Path):
+        """Calculates and saves the SHAP summary data to a CSV file."""
+        mean_abs_shap = np.abs(shap_values_for_summary).mean(axis=0)
+        
+        # Create default feature names if none are provided
+        current_feature_names = feature_names
+        if current_feature_names is None:
+            current_feature_names = [f'feature_{i}' for i in range(len(mean_abs_shap))]
+        
+        summary_df = pd.DataFrame({
+            SHAPKeys.FEATURE_COLUMN: feature_names,
+            SHAPKeys.SHAP_VALUE_COLUMN: mean_abs_shap
+        }).sort_values(SHAPKeys.SHAP_VALUE_COLUMN, ascending=False)
+        
+        summary_df.to_csv(save_path, index=False)
+        # print(f"📝 SHAP summary data saved as '{save_path.name}'")
+    
+            
     #START_O
 
     explainer = shap.TreeExplainer(model)

ml_tools/keys.py

@@ -38,11 +38,34 @@ class PyTorchInferenceKeys:
     PROBABILITIES = "probabilities"
 
 
-class PytorchModelKeys:
-    """Keys for saving and loading models"""
+class PytorchModelArchitectureKeys:
+    """Keys for saving and loading model architecture."""
     MODEL = 'model_class'
     CONFIG = "config"
-    SAVENAME = "architecture.json"
+    SAVENAME = "architecture"
+
+
+class PytorchArtifactPathKeys:
+    """Keys for model artifact paths."""
+    FEATURES_PATH = "feature_names_path"
+    TARGETS_PATH = "target_names_path"
+    ARCHITECTURE_PATH = "model_architecture_path"
+    WEIGHTS_PATH = "model_weights_path"
+    SCALER_PATH = "scaler_path"
+
+
+class DatasetKeys:
+    """Keys for saving dataset artifacts"""
+    FEATURE_NAMES = "feature_names"
+    TARGET_NAMES = "target_names"
+    SCALER_PREFIX = "scaler_"
+
+
+class SHAPKeys:
+    """Keys for SHAP functions"""
+    FEATURE_COLUMN = "feature"
+    SHAP_VALUE_COLUMN = "mean_abs_shap_value"
+    SAVENAME = "shap_summary"
 
 
 class _OneHotOtherPlaceholder:

ml_tools/path_manager.py

@@ -13,6 +13,7 @@ __all__ = [
     "sanitize_filename",
     "list_csv_paths",
     "list_files_by_extension",
+    "list_subdirectories"
 ]
 
 
@@ -385,5 +386,37 @@ def list_files_by_extension(directory: Union[str,Path], extension: str, verbose:
     return name_path_dict
 
 
+def list_subdirectories(root_dir: Union[str,Path], verbose: bool=True) -> dict[str, Path]:
+    """
+    Scans a directory and returns a dictionary of its immediate subdirectories.
+
+    Args:
+        root_dir (str | Path): The path to the directory to scan.
+        verbose (bool): If True, prints the number of directories found. 
+
+    Returns:
+        dict[str, Path]: A dictionary mapping subdirectory names (str) to their full Path objects.
+    """
+    root_path = make_fullpath(root_dir, enforce="directory")
+    
+    directories = [p.resolve() for p in root_path.iterdir() if p.is_dir()]
+    
+    if len(directories) < 1:
+        _LOGGER.error(f"No subdirectories found inside '{root_path}'")
+        raise IOError()
+    
+    if verbose:
+        count = len(directories)
+        # Use pluralization for better readability
+        plural = 'ies' if count != 1 else 'y'
+        print(f"Found {count} subdirector{plural} in '{root_path.name}'.")
+    
+    # Create a dictionary where the key is the directory's name (a string)
+    # and the value is the full Path object.
+    dir_map = {p.name: p for p in directories}
+    
+    return dir_map
+
+
 def info():
     _script_info(__all__)

ml_tools/utilities.py

@@ -6,9 +6,10 @@ from pathlib import Path
 from typing import Literal, Union, Sequence, Optional, Any, Iterator, Tuple, overload
 import joblib
 from joblib.externals.loky.process_executor import TerminatedWorkerError
-from .path_manager import sanitize_filename, make_fullpath, list_csv_paths
+from .path_manager import sanitize_filename, make_fullpath, list_csv_paths, list_files_by_extension, list_subdirectories
 from ._script_info import _script_info
 from ._logger import _LOGGER
+from .keys import DatasetKeys, PytorchModelArchitectureKeys, PytorchArtifactPathKeys, SHAPKeys
 
 
 # Keep track of available tools
@@ -24,7 +25,9 @@ __all__ = [
     "deserialize_object",
     "distribute_dataset_by_target",
     "train_dataset_orchestrator",
-    "train_dataset_yielder"
+    "train_dataset_yielder",
+    "find_model_artifacts",
+    "select_features_by_shap"
 ]
 
 
@@ -32,6 +35,7 @@ __all__ = [
 @overload
 def load_dataframe(
     df_path: Union[str, Path], 
+    use_columns: Optional[list[str]] = None, 
     kind: Literal["pandas"] = "pandas",
     all_strings: bool = False,
     verbose: bool = True
@@ -42,7 +46,8 @@ def load_dataframe(
 @overload
 def load_dataframe(
     df_path: Union[str, Path], 
-    kind: Literal["polars"],
+    use_columns: Optional[list[str]] = None,
+    kind: Literal["polars"] = "polars",
     all_strings: bool = False,
     verbose: bool = True
 ) -> Tuple[pl.DataFrame, str]:
@@ -50,6 +55,7 @@ def load_dataframe(
 
 def load_dataframe(
     df_path: Union[str, Path], 
+    use_columns: Optional[list[str]] = None,
     kind: Literal["pandas", "polars"] = "pandas",
     all_strings: bool = False,
     verbose: bool = True
@@ -58,11 +64,13 @@ def load_dataframe(
     Load a CSV file into a DataFrame and extract its base name.
 
     Can load data as either a pandas or a polars DataFrame. Allows for loading all
-    columns as string types to prevent type inference errors.
+    columns or a subset of columns as string types to prevent type inference errors.
 
     Args:
         df_path (str, Path): 
             The path to the CSV file.
+        use_columns (list[str] | None):
+            If provided, only these columns will be loaded from the CSV.
         kind ("pandas", "polars"): 
             The type of DataFrame to load. Defaults to "pandas".
         all_strings (bool): 
@@ -76,28 +84,43 @@ def load_dataframe(
             
     Raises:
         FileNotFoundError: If the file does not exist at the given path.
-        ValueError: If the DataFrame is empty or an invalid 'kind' is provided.
+        ValueError: If the DataFrame is empty, an invalid 'kind' is provided, or a column in 'use_columns' is not found in the file.
     """
     path = make_fullpath(df_path)
     
     df_name = path.stem
 
-    if kind == "pandas":
-        if all_strings:
-            df = pd.read_csv(path, encoding='utf-8', dtype=str)
-        else:
-            df = pd.read_csv(path, encoding='utf-8')
-            
-    elif kind == "polars":
-        if all_strings:
-            df = pl.read_csv(path, infer_schema=False)
+    try:
+        if kind == "pandas":
+            pd_kwargs: dict[str,Any]
+            pd_kwargs = {'encoding': 'utf-8'}
+            if use_columns:
+                pd_kwargs['usecols'] = use_columns
+            if all_strings:
+                pd_kwargs['dtype'] = str
+                
+            df = pd.read_csv(path, **pd_kwargs)
+
+        elif kind == "polars":
+            pl_kwargs: dict[str,Any]
+            pl_kwargs = {}
+            if use_columns:
+                pl_kwargs['columns'] = use_columns
+                
+            if all_strings:
+                pl_kwargs['infer_schema'] = False
+            else:
+                pl_kwargs['infer_schema_length'] = 1000
+                
+            df = pl.read_csv(path, **pl_kwargs)
+
         else:
-            # Default behavior: infer the schema.
-            df = pl.read_csv(path, infer_schema_length=1000)
+            _LOGGER.error(f"Invalid kind '{kind}'. Must be one of 'pandas' or 'polars'.")
+            raise ValueError()
             
-    else:
-        _LOGGER.error(f"Invalid kind '{kind}'. Must be one of 'pandas' or 'polars'.")
-        raise ValueError()
+    except (ValueError, pl.exceptions.ColumnNotFoundError) as e:
+        _LOGGER.error(f"Failed to load '{df_name}'. A specified column may not exist in the file.")
+        raise e
 
     # This check works for both pandas and polars DataFrames
     if df.shape[0] == 0:
@@ -109,7 +132,6 @@ def load_dataframe(
     
     return df, df_name # type: ignore
 
-
 def yield_dataframes_from_dir(datasets_dir: Union[str,Path], verbose: bool=True):
     """
     Iterates over all CSV files in a given directory, loading each into a Pandas DataFrame.
@@ -560,5 +582,205 @@ def train_dataset_yielder(
         yield (df_features, df_target, feature_names, target_col)
 
 
+def find_model_artifacts(target_directory: Union[str,Path], load_scaler: bool, verbose: bool=False) -> list[dict[str,Any]]:
+    """
+    Scans subdirectories to find paths to model weights, target names, feature names, and model architecture. Optionally an scaler path if `load_scaler` is True.
+
+    This function operates on a specific directory structure. It expects the
+    `target_directory` to contain one or more subdirectories, where each
+    subdirectory represents a single trained model result.
+
+    The expected directory structure for each model is as follows:
+    ```
+        target_directory
+        ├── model_1
+        │   ├── *.pth
+        │   ├── scaler_*.pth          (Required if `load_scaler` is True)
+        │   ├── feature_names.txt
+        │   ├── target_names.txt
+        │   └── architecture.json
+        └── model_2/
+            └── ...
+    ```
+
+    Args:
+        target_directory (str | Path): The path to the root directory that contains model subdirectories.
+        load_scaler (bool): If True, the function requires and searches for a scaler file (`.pth`) in each model subdirectory.
+        verbose (bool): If True, enables detailed logging during the file paths search process.
+
+    Returns:
+        (list[dict[str, Path]]): A list of dictionaries, where each dictionary
+            corresponds to a model found in a subdirectory. The dictionary
+            maps standardized keys to the absolute paths of the model's
+            artifacts (weights, architecture, features, targets, and scaler).
+            The scaler path will be `None` if `load_scaler` is False.
+    """
+    # validate directory
+    root_path = make_fullpath(target_directory, enforce="directory")
+    
+    # store results
+    all_artifacts: list[dict] = list()
+    
+    # find model directories
+    result_dirs_dict = list_subdirectories(root_dir=root_path, verbose=verbose)
+    for dir_name, dir_path in result_dirs_dict.items():
+        # find files
+        model_pth_dict = list_files_by_extension(directory=dir_path, extension="pth", verbose=verbose)
+        
+        # restriction
+        if load_scaler:
+            if len(model_pth_dict) != 2:
+                _LOGGER.error(f"Directory {dir_path} should contain exactly 2 '.pth' files: scaler and weights.")
+                raise IOError()
+        else:
+            if len(model_pth_dict) != 1:
+                _LOGGER.error(f"Directory {dir_path} should contain exactly 1 '.pth' file: weights.")
+                raise IOError()
+        
+        ##### Scaler and Weights #####
+        scaler_path = None
+        weights_path = None
+        
+        # load weights and scaler if present
+        for pth_filename, pth_path in model_pth_dict.items():
+            if load_scaler and pth_filename.lower().startswith(DatasetKeys.SCALER_PREFIX):
+                scaler_path = pth_path
+            else:
+                weights_path = pth_path
+        
+        # validation
+        if not weights_path:
+            _LOGGER.error(f"Error parsing the model weights path from '{dir_name}'")
+            raise IOError()
+        
+        if load_scaler and not scaler_path:
+            _LOGGER.error(f"Error parsing the scaler path from '{dir_name}'")
+            raise IOError()
+        
+        ##### Target and Feature names #####
+        target_names_path = None
+        feature_names_path = None
+        
+        # load feature and target names
+        model_txt_dict = list_files_by_extension(directory=dir_path, extension="txt", verbose=verbose)
+        
+        for txt_filename, txt_path in model_txt_dict.items():
+            if txt_filename == DatasetKeys.FEATURE_NAMES:
+                feature_names_path = txt_path
+            elif txt_filename == DatasetKeys.TARGET_NAMES:
+                target_names_path = txt_path
+        
+        # validation
+        if not target_names_path or not feature_names_path:
+            _LOGGER.error(f"Error parsing features path or targets path from '{dir_name}'")
+            raise IOError()
+        
+        ##### load model architecture path #####
+        architecture_path = None
+        
+        model_json_dict = list_files_by_extension(directory=dir_path, extension="json", verbose=verbose)
+        
+        for json_filename, json_path in model_json_dict.items():
+            if json_filename == PytorchModelArchitectureKeys.SAVENAME:
+                architecture_path = json_path
+        
+        # validation
+        if not architecture_path:
+            _LOGGER.error(f"Error parsing the model architecture path from '{dir_name}'")
+            raise IOError()
+        
+        ##### Paths dictionary #####
+        parsing_dict = {
+            PytorchArtifactPathKeys.WEIGHTS_PATH: weights_path,
+            PytorchArtifactPathKeys.ARCHITECTURE_PATH: architecture_path,
+            PytorchArtifactPathKeys.FEATURES_PATH: feature_names_path,
+            PytorchArtifactPathKeys.TARGETS_PATH: target_names_path,
+            PytorchArtifactPathKeys.SCALER_PATH: scaler_path
+        }
+        
+        all_artifacts.append(parsing_dict)
+    
+    return all_artifacts
+
+
+def select_features_by_shap(
+    root_directory: Union[str, Path],
+    shap_threshold: float = 1.0,
+    verbose: bool = True) -> list[str]:
+    """
+    Scans subdirectories to find SHAP summary CSVs, then extracts feature
+    names whose mean absolute SHAP value meets a specified threshold.
+
+    This function is useful for automated feature selection based on feature
+    importance scores aggregated from multiple models.
+
+    Args:
+        root_directory (Union[str, Path]):
+            The path to the root directory that contains model subdirectories.
+        shap_threshold (float):
+            The minimum mean absolute SHAP value for a feature to be included
+            in the final list.
+
+    Returns:
+        list[str]:
+            A single, sorted list of unique feature names that meet the
+            threshold criteria across all found files.
+    """
+    if verbose:
+        _LOGGER.info(f"Starting feature selection with SHAP threshold >= {shap_threshold}")
+    root_path = make_fullpath(root_directory, enforce="directory")
+
+    # --- Step 2: Directory and File Discovery ---
+    subdirectories = list_subdirectories(root_dir=root_path, verbose=False)
+    
+    shap_filename = SHAPKeys.SAVENAME + ".csv"
+
+    valid_csv_paths = []
+    for dir_name, dir_path in subdirectories.items():
+        expected_path = dir_path / shap_filename
+        if expected_path.is_file():
+            valid_csv_paths.append(expected_path)
+        else:
+            _LOGGER.warning(f"No '{shap_filename}' found in subdirectory '{dir_name}'.")
+    
+    if not valid_csv_paths:
+        _LOGGER.error(f"Process halted: No '{shap_filename}' files were found in any subdirectory.")
+        return []
+
+    if verbose:
+        _LOGGER.info(f"Found {len(valid_csv_paths)} SHAP summary files to process.")
+
+    # --- Step 3: Data Processing and Feature Extraction ---
+    master_feature_set = set()
+    for csv_path in valid_csv_paths:
+        try:
+            df, _ = load_dataframe(csv_path, kind="pandas", verbose=False)
+            
+            # Validate required columns
+            required_cols = {SHAPKeys.FEATURE_COLUMN, SHAPKeys.SHAP_VALUE_COLUMN}
+            if not required_cols.issubset(df.columns):
+                _LOGGER.warning(f"Skipping '{csv_path}': missing required columns.")
+                continue
+
+            # Filter by threshold and extract features
+            filtered_df = df[df[SHAPKeys.SHAP_VALUE_COLUMN] >= shap_threshold]
+            features = filtered_df[SHAPKeys.FEATURE_COLUMN].tolist()
+            master_feature_set.update(features)
+
+        except (ValueError, pd.errors.EmptyDataError):
+            _LOGGER.warning(f"Skipping '{csv_path}' because it is empty or malformed.")
+            continue
+        except Exception as e:
+            _LOGGER.error(f"An unexpected error occurred while processing '{csv_path}': {e}")
+            continue
+
+    # --- Step 4: Finalize and Return ---
+    final_features = sorted(list(master_feature_set))
+    if verbose:
+        _LOGGER.info(f"Selected {len(final_features)} unique features across all files.")
+    
+    return final_features
+
+
 def info():
     _script_info(__all__)